Esther H. Chung

Los Angeles, CA 323-***-**** Email: ad0rb9@r.postjobfree.com

Linkedin Portfolio Github U.S. Citizen

Data Scientist and Visualization/Automation expert with 2+ years of professional experience in Finance and Leading Global Brands EDUCATION

UCLA ANDERSON SCHOOL OF MANAGEMENT Los Angeles, CA MS, in Business Analytics (MSBA) Expected December 2023 Merit-based Scholarship Recipient

Customer Analytics, Optimization, Data Visualization, Forecasting and Time Series, Retail Analytics, Machine Learning SOGANG UNIVERSITY Seoul, Korea

BS, Data Analytics/Economics February 2022

Dean’s List; Magna Cum Laude; Served as TA for Advanced Python Programming course PROFESSIONAL EXPERIENCE

FEDERAL RESERVE BANK OF BOSTON

Spring Data Scientist Boston, MA (Remote) Feb – May 2023

• Conducted Python-based EDA on Federal Reserve Consumer Payment Choice survey encompassing 30,000 rows and integrated relevant datasets, resulting in 15% reduction in the time required to identify transaction behavior patterns for 2021-2022

• Engineered and presented an interactive Tableau dashboard with dynamic filters, optimizing resource utilization by 20% and delivering critical insights to non-technical senior stakeholders, addressing the preferences of 12 demographic groups on 6 payment methods in preparation for the “FedNow” instant payment service launch Fall Data Scientist Boston, MA (Remote) Sep – Present 2023

• Drove geospatial analysis by creating a fully automated data pipeline in SQL & Google Cloud Platform, significantly boosting efficiency with a remarkable reduction of 90% in processing time and enhancing accuracy by implementing the haversine formula in Python for pinpoint accuracy in detecting the coordinates of 300,000 bank locations

• Planned and directed the implementation of Tableau policy map revealing correlations between per capita income and bank counts in diverse cities, enabling persuasive presentations to financial institutions and optimal location selections for FedNow, ultimately resulting in 50% surge in adoption rate NIKE Consumer Insights Applied Analytics Graduate Intern Beaverton, OR Jun – Aug 2023 Project: Content Best Practices – Global Nike App

• Executed Linear Regression models and ANOVA in Python, uncovering the statistical significance of 20+ content attributes and their optimal combinations tailored to 6 business cases, and identifying specific target engagement metrics for each, leading to an average increase of 12% in CTRs (click-through rate) across scenarios

• Employed a meticulous Random Forest Regressor model to predict engagement level, achieving a improvement of over 15% in RMSE (root mean squared error), by incorporating new variables such as the relative location of videos and text heaviness

• Delivered findings to an audience of 60+ internal and external stakeholders, establishing a strong foundation for potential integration into app content strategies, resulting in 20% increase in user interactions and revenue generation KOREA CREDIT DATA Data Analyst Seoul, Korea Jan – Sep 2022

• Implemented an ETL pipeline in Snowflake to manage data from 1.8M+ Korean business users of a mobile app, resulting in a 40% reduction in data processing time and enabling efficient tracking of user behavior through visualizing page flows across various marketing channels using Amplitude

• Facilitated data-driven solutions, leveraging KMeans Clustering for feature segmentation within subdivided regions and business sections, leading to an extraordinary 300% increase in CTR within just one month for targeted mobile app pushes UNIVERSITY OF MICHIGAN Web Data Scraping Research Assistant Ann Arbor, MI (Remote) Sep – Dec 2022

• Constructed a Python-based web scraper using selenium chromedriver to collect historical conference information comprising 4M+ rows, and cleaned dataset by reducing dimensions and applying NLP (Stemming, Lemmatization) to text type columns, achieving 80% reduction in resource costs by eliminating redundancy and enhancing the efficiency of data mining process TECHNICAL SKILLS

Languages: SQL, Python (Pandas, NumPy, TensorFlow/Keras, Statsmodels, Scikit-learn, BeautifulSoup, Selenium), R, C++, Java Software: Jupyter, Spark, Hadoop, Tableau, AWS, Git, Gurobi, Snowflake, Confluence, Amplitude, Microsoft Products Analytics: Data Mining/Warehousing, Visualization, A/B Testing, Regression Analysis, Machine Learning, Product Management DATA ANALYTICS PROJECTS

• Correlation Analysis of ESG Index and Corporate Return KMeans Clustering, PCA Analysis, TSNE, yfinance

• Image Classification with CNN: Recognizing Clothing Categories Keras, Tensorflow, CNN(Convolutional Neural Network)

• Historical Land Information Web Scraper Pandas, Numpy, BeautifulSoup, Selenium Webdriver, Exception Handling